reuse-surface/tests/test_federation.py

from __future__ import annotations

from pathlib import Path
from unittest.mock import patch

import urllib.error
import yaml

from reuse_surface.federation import (
    compose_federated_index,
    fetch_remote_index_text,
    load_federation_manifest,
    resolve_source_index_path,
)

ROOT = Path(__file__).resolve().parent.parent

REMOTE_INDEX = """
version: 1
domain: helix_forge
updated: "2026-06-15"
capabilities:
  - id: capability.remote.sample
    name: Remote Sample
    domain: helix_forge
    vector: D2/A0/C0/R0
    owner: example
    path: registry/capabilities/capability.remote.sample.md
    summary: Sample capability from a remote index
    tags: [sample]
    consumption_modes: [planning]
"""


def _remote_manifest() -> dict:
    return {
        "version": 1,
        "domain": "helix_forge",
        "collision_policy": "warn",
        "sources": [
            {
                "repo": "local",
                "index": "registry/indexes/capabilities.yaml",
                "enabled": True,
                "required": True,
            },
            {
                "repo": "remote-repo",
                "url": "https://example.com/capabilities.yaml",
                "enabled": True,
                "required": False,
                "cache_ttl_seconds": 3600,
            },
        ],
    }


def test_manifest_with_url_source_validates():
    manifest = _remote_manifest()
    schema_path = ROOT / "schemas" / "federation.schema.yaml"
    from jsonschema import Draft202012Validator

    schema = yaml.safe_load(schema_path.read_text(encoding="utf-8"))
    errors = list(Draft202012Validator(schema).iter_errors(manifest))
    assert errors == []


def test_fetch_remote_index_text():
    source = {"repo": "remote-repo", "url": "https://example.com/capabilities.yaml"}
    payload = REMOTE_INDEX.encode("utf-8")

    class FakeResponse:
        def __enter__(self):
            return self

        def __exit__(self, *args):
            return False

        def read(self):
            return payload

    with patch("urllib.request.urlopen", return_value=FakeResponse()):
        text = fetch_remote_index_text(source["url"], source)
    assert "capability.remote.sample" in text


def test_remote_fetch_writes_cache(tmp_path, monkeypatch):
    monkeypatch.setattr("reuse_surface.federation.CACHE_DIR", tmp_path / "cache")
    source = {
        "repo": "remote-repo",
        "url": "https://example.com/capabilities.yaml",
        "cache_ttl_seconds": 3600,
    }
    payload = REMOTE_INDEX.encode("utf-8")

    class FakeResponse:
        def __enter__(self):
            return self

        def __exit__(self, *args):
            return False

        def read(self):
            return payload

    with patch("urllib.request.urlopen", return_value=FakeResponse()):
        path, warnings = resolve_source_index_path(source)
    assert path is not None
    assert warnings == []
    assert path.exists()
    assert "capability.remote.sample" in path.read_text(encoding="utf-8")


def test_remote_fetch_uses_fresh_cache_without_refetch(tmp_path, monkeypatch):
    monkeypatch.setattr("reuse_surface.federation.CACHE_DIR", tmp_path / "cache")
    source = {
        "repo": "remote-repo",
        "url": "https://example.com/capabilities.yaml",
        "cache_ttl_seconds": 3600,
    }
    payload = REMOTE_INDEX.encode("utf-8")

    class FakeResponse:
        def __enter__(self):
            return self

        def __exit__(self, *args):
            return False

        def read(self):
            return payload

    with patch("urllib.request.urlopen", return_value=FakeResponse()) as urlopen:
        resolve_source_index_path(source)
        path, warnings = resolve_source_index_path(source)
    assert warnings == []
    assert path is not None
    urlopen.assert_called_once()


def test_remote_fetch_falls_back_to_stale_cache(tmp_path, monkeypatch):
    monkeypatch.setattr("reuse_surface.federation.CACHE_DIR", tmp_path / "cache")
    source = {
        "repo": "remote-repo",
        "url": "https://example.com/capabilities.yaml",
        "cache_ttl_seconds": 0,
    }
    payload = REMOTE_INDEX.encode("utf-8")

    class FakeResponse:
        def __enter__(self):
            return self

        def __exit__(self, *args):
            return False

        def read(self):
            return payload

    with patch("urllib.request.urlopen", return_value=FakeResponse()):
        resolve_source_index_path(source)

    with patch(
        "urllib.request.urlopen",
        side_effect=urllib.error.URLError("network down"),
    ):
        path, warnings = resolve_source_index_path(source)
    assert path is not None
    assert any("stale cache" in warning for warning in warnings)


def test_compose_merges_remote_capabilities(tmp_path, monkeypatch):
    monkeypatch.setattr("reuse_surface.federation.CACHE_DIR", tmp_path / "cache")
    source = {
        "repo": "remote-repo",
        "url": "https://example.com/capabilities.yaml",
        "enabled": True,
        "cache_ttl_seconds": 3600,
    }
    payload = REMOTE_INDEX.encode("utf-8")

    class FakeResponse:
        def __enter__(self):
            return self

        def __exit__(self, *args):
            return False

        def read(self):
            return payload

    manifest = _remote_manifest()
    with patch("urllib.request.urlopen", return_value=FakeResponse()):
        federated, warnings = compose_federated_index(manifest)
    ids = {item["id"] for item in federated["capabilities"]}
    assert "capability.remote.sample" in ids
    assert "capability.registry.register" in ids
    remote = next(
        item for item in federated["capabilities"] if item["id"] == "capability.remote.sample"
    )
    assert remote["source_repo"] == "remote-repo"
    assert remote["source_url"] == "https://example.com/capabilities.yaml"


def test_load_production_manifest_still_validates():
    manifest = load_federation_manifest()
    assert manifest["domain"] == "helix_forge"
    assert any(source["repo"] == "reuse-surface" for source in manifest["sources"])

def _compose_with_remote_body(body: str, tmp_path, monkeypatch):
    """Compose with the remote member index serving `body` verbatim."""
    monkeypatch.setattr("reuse_surface.federation.CACHE_DIR", tmp_path / "cache")
    payload = body.encode("utf-8")

    class FakeResponse:
        def __enter__(self):
            return self

        def __exit__(self, *args):
            return False

        def read(self):
            return payload

    with patch("urllib.request.urlopen", return_value=FakeResponse()):
        return compose_federated_index(_remote_manifest())


def _local_ids_survived(federated) -> bool:
    return any(item["source_repo"] == "local" for item in federated["capabilities"])


def test_compose_skips_capability_without_id(tmp_path, monkeypatch):
    body = """
version: 1
domain: helix_forge
capabilities:
  - type: library
    title: No id at all
  - id: capability.remote.sample
    name: Remote Sample
"""
    federated, warnings = _compose_with_remote_body(body, tmp_path, monkeypatch)
    ids = {item["id"] for item in federated["capabilities"]}
    assert "capability.remote.sample" in ids
    assert _local_ids_survived(federated)
    assert any("remote-repo" in w and "no id" in w for w in warnings)


def test_compose_skips_non_mapping_index(tmp_path, monkeypatch):
    federated, warnings = _compose_with_remote_body(
        "just a string, not a mapping\n", tmp_path, monkeypatch
    )
    assert _local_ids_survived(federated)
    assert any("not a mapping" in w for w in warnings)


def test_compose_skips_empty_index(tmp_path, monkeypatch):
    federated, warnings = _compose_with_remote_body("", tmp_path, monkeypatch)
    assert _local_ids_survived(federated)
    assert any("remote-repo" in w for w in warnings)


def test_compose_skips_unparseable_index(tmp_path, monkeypatch):
    federated, warnings = _compose_with_remote_body(
        "capabilities: [unclosed\n", tmp_path, monkeypatch
    )
    assert _local_ids_survived(federated)
    assert any("unparseable" in w for w in warnings)


def test_compose_skips_capabilities_not_a_list(tmp_path, monkeypatch):
    federated, warnings = _compose_with_remote_body(
        "version: 1\ncapabilities: not-a-list\n", tmp_path, monkeypatch
    )
    assert _local_ids_survived(federated)
    assert any("not a list" in w for w in warnings)


def test_malformed_source_still_listed_with_zero_count(tmp_path, monkeypatch):
    federated, _ = _compose_with_remote_body(
        "just a string, not a mapping\n", tmp_path, monkeypatch
    )
    remote = next(s for s in federated["sources"] if s["repo"] == "remote-repo")
    assert remote["count"] == 0


def test_scope_shaped_row_names_the_mistake(tmp_path, monkeypatch):
    """A SCOPE.md capability block copied into an index should say so."""
    body = """
version: 1
domain: helix_forge
capabilities:
  - type: library
    title: Evidence-to-target binding
    description: Links evidence items to structured targets.
    keywords: [evidence, binding]
"""
    _, warnings = _compose_with_remote_body(body, tmp_path, monkeypatch)
    hint = next(w for w in warnings if "remote-repo" in w)
    assert "SCOPE.md capability block" in hint
    assert "id/name/summary" in hint


def test_plain_missing_id_gets_no_scope_hint(tmp_path, monkeypatch):
    body = """
version: 1
capabilities:
  - name: Has a name but no id
    summary: Something
"""
    _, warnings = _compose_with_remote_body(body, tmp_path, monkeypatch)
    hint = next(w for w in warnings if "remote-repo" in w)
    assert "has no id" in hint
    assert "SCOPE.md" not in hint